English
Related papers

Related papers: Self-StrAE at SemEval-2024 Task 1: Making Self-Str…

200 papers

Textual graphs are ubiquitous in real-world applications, featuring rich text information with complex relationships, which enables advanced research across various fields. Textual graph representation learning aims to generate…

Machine Learning · Computer Science 2024-08-22 Wenbin Hu , Huihao Jing , Qi Hu , Haoran Li , Yangqiu Song

In this paper, we present a novel neuroevolutionary method to identify the architecture and hyperparameters of convolutional autoencoders. Remarkably, we used a hypervolume indicator in the context of neural architecture search for…

Neural and Evolutionary Computing · Computer Science 2021-06-23 Daniel Dimanov , Emili Balaguer-Ballester , Colin Singleton , Shahin Rostami

Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently been shown that SAEs…

Machine Learning · Computer Science 2025-05-23 Soham Gadgil , Chris Lin , Su-In Lee

Sparse autoencoders (SAEs) have emerged as powerful techniques for interpretability of large language models (LLMs), aiming to decompose hidden states into meaningful semantic features. While several SAE variants have been proposed, there…

Machine Learning · Computer Science 2025-10-03 Xudong Zhu , Mohammad Mahdi Khalili , Zhihui Zhu

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Machine Learning · Computer Science 2026-03-17 Thibault Formal , Maxime Louis , Hervé Dejean , Stéphane Clinchant

Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised…

Computation and Language · Computer Science 2021-09-13 Kexin Wang , Nils Reimers , Iryna Gurevych

Bottleneck autoencoders have been actively researched as a solution to image compression tasks. However, we observed that bottleneck autoencoders produce subjectively low quality reconstructed images. In this work, we explore the ability of…

Computer Vision and Pattern Recognition · Computer Science 2018-01-25 Yijing Watkins , Mohammad Sayeh , Oleksandr Iaroshenko , Garrett Kenyon

In Materials Science, material development involves evaluating and optimizing the internal structures of the material, generically referred to as microstructures. Microstructures structure is stochastic, analogously to image textures. A…

Machine Learning · Computer Science 2024-08-06 Sayed Sajad Hashemi , Michael Guerzhoy , Noah H. Paulson

Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…

Artificial Intelligence · Computer Science 2026-05-19 Ouns El Harzli , Hugo Wallner , Yoonsoo Nam , Haixuan Xavier Tao

Ensemble of predictions is known to perform better than individual predictions taken separately. However, for tasks that require heavy computational resources, e.g. semantic segmentation, creating an ensemble of learners that needs to be…

Computer Vision and Pattern Recognition · Computer Science 2022-03-23 Walid Bousselham , Guillaume Thibault , Lucas Pagano , Archana Machireddy , Joe Gray , Young Hwan Chang , Xubo Song

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Philipp Wesp , Robbie Holland , Vasiliki Sideri-Lampretsa , Sergios Gatidis

In the last few years there have been important advancements in generative models with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). However, standard Autoencoders (AEs) and…

Computer Vision and Pattern Recognition · Computer Science 2019-07-26 Massimiliano Patacchiola , Patrick Fox-Roberts , Edward Rosten

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Machine Learning · Computer Science 2026-05-12 Collin Francel

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Machine Learning · Computer Science 2025-12-08 Antonio Bărbălau , Cristian Daniel Păduraru , Teodor Poncu , Alexandru Tifrea , Elena Burceanu

Given a convolutional dictionary underlying a set of observed signals, can a carefully designed auto-encoder recover the dictionary in the presence of noise? We introduce an auto-encoder architecture, termed constrained recurrent sparse…

Machine Learning · Computer Science 2018-07-13 Bahareh Tolooshams , Sourav Dey , Demba Ba

Neural audio codecs and autoencoders have emerged as versatile models for audio compression, transmission, feature-extraction, and latent-space generation. However, a key limitation is that most are trained to maximize reconstruction…

Sound · Computer Science 2025-09-10 Dimitrios Bralios , Jonah Casebeer , Paris Smaragdis

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-scale datasets to learn clear behavioral information, which…

Machine Learning · Computer Science 2025-10-06 Anyi Wang , Xuansheng Wu , Dong Shu , Yunpu Ma , Ninghao Liu